The Bentham Project has been experimenting with the Handwritten Text Recognition (HTR) of Bentham’s manuscripts for the past five years, first as a partner in the tranScriptorium project and now as part of READ.

Read about our progress with HTR and the Transkribus platform in blog posts from June 2017 and  February 2018.

Keyword Spotting

Our results have thus far been impressive, especially considering the immense difficulty of Bentham’s own handwriting.  But automated transcription is not yet at a point where it is sufficiently accurate to be used by Bentham Project researchers as a basis for scholarly editing.  It would be too time-consuming (and probably too irritating!) for us to correct the errors in the computer-generated transcripts of papers written in Bentham’s hand.

However, the current state of the technology is strong enough for keyword searching!  And thanks to a collaboration with the PRHLT research center at the Universitat Politècnica de València (another partner in the READ project) we have some exciting new results to report.  It is now possible to search over 90,000 digital images of the central collections of Bentham’s manuscripts, which are held at Special Collections University College London and The British Library.

• Start searching!
• Searching guidelines
• Record your searches on our Google sheet

A Keyword Spotting search for the word ‘pleasure’

Appeal for volunteers!

I have prepared a Google sheet with some suggested search terms in 5 different spreadsheet tabs (Bentham’s neologisms, concepts, people, places and other).

It would be fantastic if people filled in the spreadsheet to record some of their searches, using my suggested search terms and some of their own.  Transcribers could search for subjects they are interested in and then cross-reference to material on the Transcription Desk that they might like to transcribe.

Who knows what we might find??  I hope to share some of these results in my upcoming presentation at the Transkribus User Conference in November 2018.  Thanks in advance for your participation.

Background

The PRHLT team have processed the Bentham papers with cutting-edge HTR and probabilistic word indexing technologies.  This sophisticated form of searching is often called Keyword Spotting.  It is more powerful than a conventional full-text search because it uses statistical models trained for text recognition to search through probability values assigned to character sequences (words), considering most possible readings of each word on a page.

We delivered thousands of images and transcripts to the team in Valencia and gave them access to the data we had already used to train HTR models in Transkribus.  After cleaning our data and using Transkribus technology to divide the images into lines, the team in Valencia trained neural network algorithims to recognise and index the collection.

The result is that this vast collection of Bentham’s papers can be efficiently searched, including those papers that have not yet been transcribed!  The accuracy rates are impressive.  The spots suggest around 84-94% accuracy (6-16% Character Error Rate) when compared with manual transcriptions of Bentham’s manuscripts.  More precisely speaking, laboratory tests show that the word average search precision ranges from 79% to 94%.  This means that, out of 100 average search results, only as few as 6 may fail to actually be the words searched for. The accuracy of spotted words depends on the difficulty of Bentham’s handwriting – although it is possible to find useful results in Bentham’s scrawl!  There could be as many as 25 million words waiting to be found.

Use cases

This fantastic site will be invaluable to anyone interested in Bentham’s philosophy.  It will help Bentham Project researchers to find previously unknown references in pages that have not yet been transcribed.  It will allow researchers to quickly investigate Bentham’s concepts and correspondents.  I hope that it will also help volunteer transcribers to find interesting material.

This interface is a prototype beta version.  In the future we want to increase the power of this research tool by connecting it to other digital resources, allowing users to quickly search the manuscripts at the UCL library repository, the Bentham papers database and the Transcription Desk and linking these images to our rich existing metadata.

Similar Keyword Spotting technology (based  on research by the CITlab team at the University of Rostock, another one of the READ project partners) is currently available to all users of the Transkribus platform.  Find out more at the READ project website.

I welcome any feedback on our new search functionality at: transcribe.bentham@ucl.ac.uk

My thanks go to the PRHLT research center, the University of Innsbruck and Chris Riley, Transcription Assistant at the Bentham Project for their support and assistance.

We’re in a good mood at TB HQ after successfully migrating the Transcription Desk to a new server at UCL.  Read more.

We need to say a big thank you to all of our transcribers for their patience as we iron out a few post-migration snags…

Here are the full statistics for the initiative – as of 12 October 2018.

20,934 manuscript pages have now been transcribed or partially-transcribed. Of these transcripts, 20,096 (95%) have been checked and approved by TB staff.

Over the past four weeks, volunteers have worked on a total of 112 manuscript pages. This means that an average of 28 pages have been transcribed each week during the past month.

Check out the Benthamometer for more information on how much has been transcribed from each box of Bentham’s papers!

It’s time for a second update on the transcription challenge we launched in back in July.

It has been really cheering to see so many of our volunteers responding to our request to complete the transcription of a number of targeted boxes.  Thanks to this collaborative work, we are coming close to finalising the transcription of 7 boxes of Bentham’s manuscripts.  I am hugely grateful to everyone who has participated.

Volunteers have now transcribed 104 pages of the targeted material.  This represents around 75% of the 138 pages which we asked them to transcribe.

This is a particularly impressive achievement when you consider that it is often the most difficult pages which remain untranscribed at the Transcription Desk.   Many of these pages have terrible handwriting, confusing layouts and passages of non-English text.

Volunteers have reached our target for boxes 14, 95 and 538 – yay!  And there are just 1-2 pages still to transcribe in boxes 50, 70 and 537.  Box 72 has a number of pages still to be transcribed – and we would be grateful for the help of any French-speaking volunteers.

The full list of outstanding pages can be found at the end of this blog post – we invite all our volunteers to keep transcribing!

All the transcription statistics on Transcribe Bentham are compiled manually.  So once all the targets have been reached, I will need to undertake some double-checks to ensure that each of these boxes is complete.  Then we will be able to celebrate the completion of 7 boxes of Bentham’s manuscripts and another fantastic contribution to Bentham scholarship!

If you have any questions or comments about the challenge, please let me know by email (transcribe.bentham@ucl.ac.uk).  Happy transcribing…

Material still to transcribe:

Box 50

Box 70

Box 72

Box 537

I am pleased to announce that the Transcribe Bentham Transcription Desk is open for business once more.

You can now access the site at a new web address: http://transcribe-bentham.ucl.ac.uk/

Please update your bookmarks with this new link!

The old site will have a redirect in place to direct users to the new site.

Huge thanks go to Tom Couch and his team at UCL Research IT Services, who have successfully migrated the platform onto a new server at UCL and made various updates and fixes to the Mediawiki.  We also thank Co-Sector, University of London for supporting the platform since 2010.

For our volunteers, the site will hopefully not have changed much.  You can log in and continue transcribing as normal.  All previous edits should have been preserved.

Important changes:

One noticeable difference is that the Javascript viewer is now the default mode of viewing images on the platform.  The Flash viewer is due to become obsolete by 2020 and is already blocked by default on most web browsers.  At the moment, it is still possible to view the manuscripts in the Flash viewer by clicking the options at the bottom left of an image.

Known issues:

Please bear in mind there are a few known issues with the new site.  We are working to fix the following bugs as soon as possible:

• Preview option when transcribing

The option to view a ‘clean’ version of your transcript, without visible TEI tags is currently broken.

• Emails from TB Editor

Any email notifications from TB_Editor are currently marked as being sent by an account called ‘ccea038’.  This is an admin account which is linked to the server.

I would like to thank our volunteers for their continued patience.  Good luck exploring the new site and please get in touch if you have any feedback, issues or questions (transcribe.bentham@ucl.ac.uk).

Now that the site has been migrated, we can start to daydream about further improvements that we hope to make to the platform in the future too!

Thanks to the hard work of UCL Research IT Services and Co-Sector, University of London, we are almost ready to migrate the Transcribe Bentham Transcription Desk to a new server at UCL.

The planned date of the migration is 9 October 2018. 

I hope that the migration process will not affect volunteers too much.  There will be a day or two of downtime, after which point volunteers will be able to continue transcribing as normal.

UCL Research IT services will update the Mediawiki and eliminate any bugs.  Having the platform hosted at UCL should also put us in a better position to make further technical improvements to it in the future.

Migration Timeline

8 October

• Volunteers can carry on working up until midnight on 8 October.
• All edits made by volunteers up until the end of 8 October will be preserved.

9 October

• The site will go into maintenance mode.  There will be a notice to this effect on the current site.
• Data will be migrated and tests carried out.
• Volunteers should not make any edits to the current or new site at this time – any changes made after 8 October will not be saved.

10 October

• Volunteers should wait for confirmation that the new site is ready.  This will be sent out via our email newsletter and posted on the Transcribe Bentham blog, Twitter account and Facebook page.
• Visitors to the old site will be redirected to the new web address.

I am very much looking forward to working with you all on the updated site.  If you have any questions about the migration, please get in touch.